Forecasting crisis in African countries

• Autor(a) principal: Jossefa, Anastácio Jorge
• Data de Publicação: 2022
• Tipo de documento: Dissertação
• Idioma: eng
• Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
• Texto Completo: http://hdl.handle.net/10362/143065
• topic: Banking crisis; Dynamic probit models; Early warning indicators; African countries; Domínio/Área Científica::Ciências Sociais::Economia e Gestão

Banking and systemic crises are rare events, but these have dramatic and extremely costly consequences for low-income countries. The objective of this project is to contribute to the portfolio of early warning models that are available to policy makers by exploring the intertwined dynamics in a panel dataset that includes 38 African countries over the period 1970 to 2017. In our analysis we estimate simple and dynamic probit models with three specifications and then evaluate the performance of the models used with the objective of understanding if past values of the variables impact current and future values and there for eif the dynamic probit model improved performance and predictive power. The results show that adding a dynamic component to the model significantly improves the performance of the early warning model.